Create model configuration

Create a model configuration that is referenced by the agent. This interface does not upload or save provider keys.

POST https://moi.matrixorigin.cn/newmoi/workspaces/{workspace_id}/model-configs

Before you call

Prepare a personal access token and target workspace ID that has access to the target workspace.

The example below uses:

• $AI_STUDIO_API_KEY: The actual personal access token, passed through the X-API-Key Header.

• $WORKSPACE_ID: The workspace ID of the configuration to be created, passed in the X-Workspace-ID Header and also as workspace_id in the path.

Referenced resources such as connections, credentials, etc. must be valid; the interface itself does not receive provider keys.

Request example

curl -X POST "https://moi.matrixorigin.cn/newmoi/workspaces/$WORKSPACE_ID/model-configs" \
  -H "X-API-Key: $AI_STUDIO_API_KEY" \
  -H "X-Workspace-ID: $WORKSPACE_ID" \
  -H 'Content-Type: application/json' \
  -d '{
    "name": "销售分析模型",
    "model_name": "<MODEL_NAME>",
    "model_category": "chat"
  }'

Path parameters

Parameters	Type	Is it required	Description
workspace_id	string	Yes	Current workspace ID, must be consistent with X-Workspace-ID.

Request body

Parameters	Type	Is it required	Description
name	string	Yes	Configuration name.
model_name	string	Yes	Model name.
description	string	No	Configuration description.
status	string	No	Configuration status.
source_kind	string	No	Model source type.
model_category	string	No	Model category.
provider_ref	string	No	Provider reference.
display_name	string	No	The configured display name.
connection_ref	string	No	An existing connection resource reference.
credential_ref	string	No	An existing credential reference.
parameters	object	No	Model parameters.
parameter_schema	object	No	Structural definition of model parameters.
capabilities	string[]	No	Model capabilities.
limits	object	No	Model usage restrictions.
pricing_ref	string	No	Pricing configuration reference.
labels	object	No	Tag key-value pair.
annotations	object	No	Annotation key-value pair.
metadata	object	No	Extended metadata.

[] after a type denotes an array. [] in a field path denotes each item in an array.

Successful response

Returns 201 on success. data configured for new models.

{
  "code": 0,
  "data": {
    "id": "mc_01",
    "workspace_id": "ws_01",
    "name": "销售分析模型",
    "status": "active",
    "source_kind": "workspace",
    "model_category": "chat",
    "model_name": "<MODEL_NAME>",
    "version": 1,
    "created_at": "2026-08-18T01:00:00Z",
    "updated_at": "2026-08-18T01:00:00Z"
  }
}

The response fields are as follows.

Field	Type	Description
code	integer	0 on success.
data.id	string	Model configuration ID.
data.workspace_id	string	ID of the workspace to which it belongs.
data.name	string	Configuration name.
data.status	string	Configuration status.
data.source_kind	string	Model source type.
data.model_category	string	Model category.
data.model_name	string	Model name.
data.version	integer	Configuration version.
data.created_at	string	Creation and update time.
data.updated_at	string	Creation and update time.

[] after a type denotes an array. [] in a field path denotes each item in an array.

Error response

{
  "code": 2,
  "message": "模型配置参数无效"
}

Common HTTP errors

HTTP status code	error code	Common causes	Recommended actions
400	2（INVALID_ARGUMENT）	The request body, resource reference, or model configuration field is invalid.	Check request fields and reference IDs.
401	6（UNAUTHENTICATED）	Credentials are missing or invalid.	Check API Key.
403	5（PERMISSION_DENIED）	The current identity does not have permission to create configurations in the workspace.	Use valid credentials, or contact your administrator for authorization.
409	4（ALREADY_EXISTS）	Configuration ID or name conflict.	Modify the logo or process the existing configuration.
503	15（UNAVAILABLE）	The model configuration service is unavailable.	Try again later.

Follow-up operations

Save data.id and reference the configuration in agent model binding.

Last updated on Sep 3, 2026